A New Hybrid Model of Generative Adversarial Network and You Only Look Once Algorithm for Automatic License-Plate Recognition

• URL: http://arxiv.org/abs/2509.06868v1
• Date: Mon, 08 Sep 2025 16:34:54 GMT
• Title: A New Hybrid Model of Generative Adversarial Network and You Only Look Once Algorithm for Automatic License-Plate Recognition
• Authors: Behnoud Shafiezadeh, Amir Mashmool, Farshad Eshghi, Manoochehr Kelarestaghi,
• Abstract summary: In this paper, a selective Generative Adversarial Network (GAN) is proposed for deblurring in the preprocessing step.<n>YOLOv5 achieves a detection time of 0.026 seconds for both License-Plate Detection (LPD) and Character Recognition (CR) detection stages.<n>The proposed model achieves accuracy rates of 95% and 97% in the LPD and CR detection phases, respectively.
• Score: 1.6566053195631465
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Automatic License-Plate Recognition (ALPR) plays a pivotal role in Intelligent Transportation Systems (ITS) as a fundamental element of Smart Cities. However, due to its high variability, ALPR faces challenging issues more efficiently addressed by deep learning techniques. In this paper, a selective Generative Adversarial Network (GAN) is proposed for deblurring in the preprocessing step, coupled with the state-of-the-art You-Only-Look-Once (YOLO)v5 object detection architectures for License-Plate Detection (LPD), and the integrated Character Segmentation (CS) and Character Recognition (CR) steps. The selective preprocessing bypasses unnecessary and sometimes counter-productive input manipulations, while YOLOv5 LPD/CS+CR delivers high accuracy and low computing cost. As a result, YOLOv5 achieves a detection time of 0.026 seconds for both LP and CR detection stages, facilitating real-time applications with exceptionally rapid responsiveness. Moreover, the proposed model achieves accuracy rates of 95\% and 97\% in the LPD and CR detection phases, respectively. Furthermore, the inclusion of the Deblur-GAN pre-processor significantly improves detection accuracy by nearly 40\%, especially when encountering blurred License Plates (LPs).To train and test the learning components, we generated and publicly released our blur and ALPR datasets (using Iranian license plates as a use-case), which are more representative of close-to-real-life ad-hoc situations. The findings demonstrate that employing the state-of-the-art YOLO model results in excellent overall precision and detection time, making it well-suited for portable applications. Additionally, integrating the Deblur-GAN model as a preliminary processing step enhances the overall effectiveness of our comprehensive model, particularly when confronted with blurred scenes captured by the camera as input.

Related papers

• PRISM: Performer RS-IMLE for Single-pass Multisensory Imitation Learning [51.24484551729328]
  We introduce PRISM, a single-pass policy based on a batch-global rejection-sampling variant of IMLE.<n> PRISM couples a temporal multisensory encoder with a linear-attention generator using a Performer architecture.<n>We demonstrate the efficacy of PRISM on a diverse real-world hardware suite, including loco-manipulation using a Unitree Go2 with a 7-DoF arm D1 and tabletop manipulation with a UR5 manipulator.
  arXiv  Detail & Related papers  (2026-02-02T17:57:37Z)
• Fast-COS: A Fast One-Stage Object Detector Based on Reparameterized Attention Vision Transformer for Autonomous Driving [3.617580194719686]
  This paper introduces Fast-COS, a novel single-stage object detection framework crafted specifically for driving scenes.<n> RAViT achieves 81.4% Top-1 accuracy on the ImageNet-1K dataset.<n>It surpasses leading models in efficiency, delivering up to 75.9% faster GPU inference and 1.38 higher throughput on edge devices.
  arXiv  Detail & Related papers  (2025-02-11T09:54:09Z)
• Braille Letter Reading: A Benchmark for Spatio-Temporal Pattern Recognition on Neuromorphic Hardware [50.380319968947035]
  Recent deep learning approaches have reached accuracy in such tasks, but their implementation on conventional embedded solutions is still computationally very and energy expensive. We propose a new benchmark for computing tactile pattern recognition at the edge through letters reading. We trained and compared feed-forward and recurrent spiking neural networks (SNNs) offline using back-propagation through time with surrogate gradients, then we deployed them on the Intel Loihimorphic chip for efficient inference. Our results show that the LSTM outperforms the recurrent SNN in terms of accuracy by 14%. However, the recurrent SNN on Loihi is 237 times more energy
  arXiv  Detail & Related papers  (2022-05-30T14:30:45Z)
• Scalable Vehicle Re-Identification via Self-Supervision [66.2562538902156]
  Vehicle Re-Identification is one of the key elements in city-scale vehicle analytics systems. Many state-of-the-art solutions for vehicle re-id mostly focus on improving the accuracy on existing re-id benchmarks and often ignore computational complexity. We propose a simple yet effective hybrid solution empowered by self-supervised training which only uses a single network during inference time.
  arXiv  Detail & Related papers  (2022-05-16T12:14:42Z)
• End-to-End High Accuracy License Plate Recognition Based on Depthwise Separable Convolution Networks [0.0]
  We propose a novel segmentation-free framework for license plate recognition and introduce NP-ALPR dataset. The proposed network model consists of the latest deep learning methods and state-of-the-art ideas, and benefits from a novel network architecture. We evaluate the effectiveness of the proposed method on three different datasets and show a recognition accuracy of over 99% and over 70 fps.
  arXiv  Detail & Related papers  (2022-02-21T14:45:03Z)
• BLPnet: A new DNN model and Bengali OCR engine for Automatic License Plate Recognition [1.924182131418037]
  This paper reports a computationally efficient and reasonably accurate Automatic License Plate Recognition (ALPR) system for Bengali characters. With a Computational Neural Network (CNN)based new Bengali OCR engine, the model is characters rotation invariant. The model feeding with17 frames per second (fps) on real-time video footage can detect a vehicle with the Mean Squared Error (MSE) of 0.0152, and the mean license plate character recognition accuracy of 95%.
  arXiv  Detail & Related papers  (2022-02-18T22:58:53Z)
• Improved YOLOv5 network for real-time multi-scale traffic sign detection [4.5598087061051755]
  We propose an improved feature pyramid model, named AF-FPN, which utilize the adaptive attention module (AAM) and feature enhancement module (FEM) to reduce the information loss in the process of feature map generation. We replace the original feature pyramid network in YOLOv5 with AF-FPN, which improves the detection performance for multi-scale targets of the YOLOv5 network.
  arXiv  Detail & Related papers  (2021-12-16T11:02:12Z)
• Modelling Lips-State Detection Using CNN for Non-Verbal Communications [2.0715161308249916]
  This paper reports two new Conal Neural Network (CNN) models for lips state detection. We simplify lips-state model with a set of six key landmarks, and use their distances for the lips state classification. Varying frame-rates, lips-movements and face-angles are investigated to determine the effectiveness of the models.
  arXiv  Detail & Related papers  (2021-12-09T08:16:00Z)
• Adaptive Anomaly Detection for Internet of Things in Hierarchical Edge Computing: A Contextual-Bandit Approach [81.5261621619557]
  We propose an adaptive anomaly detection scheme with hierarchical edge computing (HEC) We first construct multiple anomaly detection DNN models with increasing complexity, and associate each of them to a corresponding HEC layer. Then, we design an adaptive model selection scheme that is formulated as a contextual-bandit problem and solved by using a reinforcement learning policy network.
  arXiv  Detail & Related papers  (2021-08-09T08:45:47Z)
• Improving Variational Autoencoder based Out-of-Distribution Detection for Embedded Real-time Applications [2.9327503320877457]
  Out-of-distribution (OD) detection is an emerging approach to address the challenge of detecting out-of-distribution in real-time. In this paper, we show how we can robustly detect hazardous motion around autonomous driving agents. Our methods significantly improve detection capabilities of OoD factors to unique driving scenarios, 42% better than state-of-the-art approaches. Our model also generalized near-perfectly, 97% better than the state-of-the-art across the real-world and simulation driving data sets experimented.
  arXiv  Detail & Related papers  (2021-07-25T07:52:53Z)
• Sample and Computation Redistribution for Efficient Face Detection [137.19388513633484]
  Training data sampling and computation distribution strategies are the keys to efficient and accurate face detection. scrfdf34 outperforms the best competitor, TinaFace, by $3.86%$ (AP at hard set) while being more than emph3$times$ faster on GPUs with VGA-resolution images.
  arXiv  Detail & Related papers  (2021-05-10T23:51:14Z)
• Anchor-free Small-scale Multispectral Pedestrian Detection [88.7497134369344]
  We propose a method for effective and efficient multispectral fusion of the two modalities in an adapted single-stage anchor-free base architecture. We aim at learning pedestrian representations based on object center and scale rather than direct bounding box predictions. Results show our method's effectiveness in detecting small-scaled pedestrians.
  arXiv  Detail & Related papers  (2020-08-19T13:13:01Z)
• SADet: Learning An Efficient and Accurate Pedestrian Detector [68.66857832440897]
  This paper proposes a series of systematic optimization strategies for the detection pipeline of one-stage detector. It forms a single shot anchor-based detector (SADet) for efficient and accurate pedestrian detection. Though structurally simple, it presents state-of-the-art result and real-time speed of $20$ FPS for VGA-resolution images.
  arXiv  Detail & Related papers  (2020-07-26T12:32:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.